Showing 2026Show all
3 papers · 1 filter
cs.CV2026
Beyond Visual Quality: Evaluating Physical Consistency under Ego-Motion with EgoGenEval
Yilin Long, Chenming Zhu, Zitang Gou +2
Recent visual generators produce high-fidelity images yet often violate physical consistency under ego-motion, limiting their use for spatial reasoning and embodied planning. Exist…
cs.CV2026
GTAM: Geometry Grounded Track Anything Model
Chenming Zhu, Peizhou Cao, Jingli Lin +5
Human spatial understanding arises from jointly perceiving geometry and semantics, enabling consistent object identification and localization across viewpoints and time. Current vi…
cs.CV2026
Thinking with Imagination: Agentic Visual Spatial Reasoning with World Simulators
Chenming Zhu, Jingli Lin, Yilin Long +4
While Vision-Language Models (VLMs) have shown strong visual reasoning capabilities, their spatial reasoning abilities remain largely constrained to the observed images and text-or…